Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to mental or emotional states or concepts like 'spirit', 'mind', 'well', 'touch', 'talk', 'guard'

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to notable individuals or leadership qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stray
    -0.66
     Flavoring
    -0.63
     Mehran
    -0.63
    Âł
    -0.59
     Aren
    -0.58
    ³³
    -0.57
     Illegal
    -0.57
     typo
    -0.56
     factual
    -0.56
     Own
    -0.55
    POSITIVE LOGITS
    sheets
    1.03
    piece
    1.00
    book
    1.00
    sheet
    0.97
    lists
    0.97
    set
    0.94
    line
    0.93
    pieces
    0.93
    frame
    0.93
    otype
    0.92
    Act Density 0.555%

    No Known Activations